Related papers: Ratchet: A Minimal Hygiene Recipe for Self-Evolvin…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…

Large Language Models (LLMs) have shown tremendous potential as agents, excelling at tasks that require multiple rounds of reasoning and interactions. Rejection Sampling Fine-Tuning (RFT) has emerged as an effective method for finetuning…

Large language models (LLMs) exhibited powerful capability in various natural language processing tasks. This work focuses on exploring LLM performance on zero-shot information extraction, with a focus on the ChatGPT and named entity…

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement…

Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…

Rapid advancements in large language models (LLMs) have the potential to assist in scientific progress. A critical capability toward this endeavor is the ability to reproduce existing work. To evaluate the ability of AI agents to reproduce…

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for…

Generative information extraction using large language models, particularly through few-shot learning, has become a popular method. Recent studies indicate that providing a detailed, human-readable guideline-similar to the annotation…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we…

As LLM agents transition to autonomous digital coworkers, maintaining deterministic goal-directedness in non-linear multi-turn conversations emerged as an architectural bottleneck. We identify and formalize a systemic failure mode termed…

Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability to complex scientific tasks. We introduce CASCADE, a self-evolving agentic framework…

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills…

Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a closed-loop…

Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks, such as program repair and issue resolution. These agents operate by autonomously generating natural language thoughts,…

With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for…